Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/scarrillo/releaseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/scarrillo/release/xcbuild)<a href="https://agentmods.dev/commands/scarrillo/release/xcbuild"><img src="https://agentmods.dev/badge/commands/scarrillo/release/xcbuild/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/scarrillo/release/xcbuild"><img src="https://agentmods.dev/badge/commands/scarrillo/release/xcbuild.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.02295 |
| Opus 5.5 | $0.00008 | $0.00918 |
| Sonnet 5.5 | $0.00004 | $0.00459 |
| Haiku 4.5 | $0.00002 | $0.00230 |
Grade A, and why
xcbuild scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xcode Build
Build an iOS app for the iOS Simulator using xcodebuild, with automatic project detection and simulator selection.
Arguments
$ARGUMENTS
- No arguments: Use cached settings or prompt for selection on first run
--change: Clear cached settings and prompt for new scheme and simulator selection--scheme=<name>: Use a specific scheme (updates cache)--id=<UUID>: Use a specific simulator UUID (one-time, doesn't update cache)
Configuration
Plugin settings are stored in dedicated config files (Claude Code's settings.json has a strict schema):
| Scope | File | Use Case |
|---|---|---|
project |
.claude/config.json |
Team defaults, version controlled |
local |
.claude/config.local.json |
Personal settings, gitignored |
Project Settings (.claude/config.json)
Team defaults, committed to version control:
{
"release-plugin": {
"xcbuild": {
"scheme": "MyApp",
"showWarnings": true
}
}
}
Local Settings (.claude/config.local.json)
Personal settings, gitignored (simulator UUIDs are machine-specific):
{
"release-plugin": {
"xcbuild": {
"simulatorId": "A2444326-C93A-4271-9EF0-C44AA5D4FC42",
"scheme": "MyApp-Dev"
}
}
}
Settings Reference
| Setting | Recommended Scope | Description |
|---|---|---|
scheme |
project | Default scheme (team default) |
simulatorId |
local | Default simulator UUID (machine-specific) |
showWarnings |
project | Show build warnings in output (default: true) |
Precedence (highest to lowest)
- Command-line arguments (
--scheme=,--id=) - Local config (
.claude/config.local.json) - Project config (
.claude/config.json) - Session cache
- Prompt user
Instructions
Step 1: Check for arguments and cached settings
Parse $ARGUMENTS:
- If
--id=<UUID>is provided, use that UUID for this build only (skip to Step 5) - If
--scheme=<name>is provided, use that scheme and update cache (proceed to Step 3) - If
--changeis provided, clear all cached settings and proceed to Step 1b - If no arguments, check settings in precedence order:
.claude/config.local.json→release-plugin.xcbuild.schemeandsimulatorId.claude/config.json→release-plugin.xcbuild.schemeandsimulatorId- Session cache from earlier in this conversation
- If scheme is missing, proceed to Step 1b (detect project, then select scheme)
- If simulator is missing, proceed to Step 3 (query and select simulator)
- If both are found, skip to Step 5 (run build - trust saved simulator ID)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago Changed · +4 tokens per session d570cb076855
- 1mo ago First seen · 271 lines · 16 tokens per session scan A 4e3d32eef504
xcbuild is a command published in the GitHub repository scarrillo/release (9 stars, last pushed 14d ago), licensed MIT. It adds 20 tokens to every session and 2,295 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
feat
Kick off tasks creation for a new feature (4-item interview before invoking pm-agent; an epic-sized requirement routes to phased decomposition, a feature already built on one platform routes to cross-platform parity, a change that touches no endpoint routes to client-only).
feasibility
Pre-design feasibility review — check a planning document's (or HTML prototype's) platform premises against current OS docs and both repos, before design is settled.
ios-test
Bu komut iOS/SwiftUI uygulamasini derleyip simulator'da acarak computer use ile gorsel test yapar.
add-accessibility
SwiftUI view'lara accessibility identifier ekle. "accessibility ekle", "identifier ekle", "test icin etiketle", "VoiceOver destegi ekle", "erisilebilirlik ekle" gibi isteklerde tetiklenir.
appstore-detect
Quick terminal commands to inspect your iOS project before running a full audit.
audit
Smart audit selector - analyzes your project and suggests relevant audits.